Module 20 – Domain III: Research

After reviewing Module 20 lecture, you should be able to:

  1. Describe types of research.
  2. Discuss statistical evaluation.

Types of research and research design

Types of research

  • basic - has no specific goal and explores the unknown
  • applied - An applied research study involves an effort to answer questions, change concepts; has a specific goal in mind or is seeking to answer a certain question

Study Designs

  • Correlational- looks for a linear relationship between variable; A correlation should be close to 1 or -1 to indicate significance; a correlation close to zero indicates little or no significance
  • Longitudinal- looks at variables overtime
  • Prospective- looks forward in time at variable which is believed to lead to specific outcome; a type of study in which the disease of interest develops after data collection has begun
  • Quantitative- looks at numerical data/results

Research Principles

  • Hypothesis – states a probable outcome to a study; the objective of research is to test the hypothesis
  • null hypothesis– states that no relationship exists among the variables being tested; research tries to reject the null hypothesis
  • Variables
  • dependent– outcome variable; the variable being tested (ie: blood pressure)
  • independent– variables which are believed to affect the dependent variable (ie: sodium intake)
  • Samples
  • random sample– drawn from entire population; all having an equal chance of being chosen
  • stratified random sample– large group broken down into subgroups based on certain characteristics; subjects are then randomly selected from subgroups; example: selected subjects in the general population and categorized them as overweight and non overweight and then randomly sample from those groups
  • A stratified sample is obtained by taking samples from each stratum or sub-group of a population; Stratified sampling techniques are generally used when the population is heterogeneous/dissimilar where certain homogeneous/similar sub-populations can be isolated (strata); Example - Suppose a farmer wishes to work out the average milk yield of each cow type in his herd which consists of Ayrshire, Friesian, Galloway and Jersey cows. He could divide up his herd into the four sub-groups and take samples from these
  • cluster sampling– samples larger group then specific subgroups
  • A multi-stage sampling scheme in which the population is first divided into clusters, then a sample of these clusters is chosen via simple random sampling, and then a simple random sample of population elements is selected within the chosen clusters. This differs from stratified sampling in that in stratified sampling, all strata are sampled, whereas in cluster sampling we take a sample of clusters, not all clusters (heterogeneity within a cluster and homogeneity between clusters
  • Bias - conscious or unconscious distortion of results by the researcher

Statistical evaluation, interpretation and application

  • Validity - the extent to which a instrument or test accurately measures what it is supposed to measure
  • Reliability - the extent to which an experiment, instrument, test, or any measuring procedure yields the same result on repeated trials
  • Accuracy - accuracy refers to the agreement between a measurement and the true or correct value; a measure of validity. If a clock strikes twelve when the sun is exactly overhead, the clock is said to be accurate.
  • Precision - precision refers to the repeatability of measurement; a measure of reliability. It does not require us to know the correct or true value. If each day for several years a clock reads exactly 10:17 AM when the sun is at the zenith, this clock is very precise.
  • Central Tendency Measurements
  • mean – average; scores are summed and divided by the number of scores
  • median – score at the middle of the distribution
  • mode – score which occurs most often
  • Variability
  • standard deviation– amount a value deviates in relation to the mean or average; normal distribution = bell shaped curve
  • Statistical methods
  • degrees of freedom– N-1; N = number in sample
  • significance level– disproves the null hypothesis; indicates a found correlation or relationship did not occur because of chance (ie: .01 level = 1 in 100 times is due to chance)
  • chi-square test– used to prove relationship between 2 variables
  • T-test – shows how far a statistic deviates from the mean and whether differences between means of groups are significant
  • p-value: – the smaller the number the more significant
  • Consider an experiment where you've measured values in two samples, and the means are different. How sure are you that the population means are different as well? There are two possibilities: (1) The populations have different means or (2) The populations have the same mean, and the difference you observed is a coincidence of random sampling
  • the P value is a probability, with a value ranging from zero to one. It is the answer to this question: If the populations really have the same mean overall, what is the probability that random sampling would lead to a difference between sample means as large (or larger) than you observed?
  • Common misinterpretation of a P value: If the P value is 0.03, that means that there is a 3% chance of observing a difference as large as you observed even if the two population means are identical. It is tempting to conclude, therefore, that there is a 97% chance that the difference you observed reflects a real difference between populations and a 3% chance that the difference is due to chance. Wrong. What you can say is that random sampling from identical populations would lead to a difference smaller than you observed in 97% of experiments and larger than you observed in 3% of experiments. You have to choose. Would you rather believe in a 3% coincidence? Or that the population means are really different?
  • A measure of probability that a difference between groups during an experiment happened by chance. For example, a p-value of .01 (p = .01) means there is a 1 in 100 chance the result occurred by chance. The lower the p-value, the more likely it is that the difference between groups was caused by treatment.

Now that you have read the lecture, consider the following:

  1. Describe types of research. Include research design.
  2. Discuss statistical evaluation. Include interpretation and application of statistics.

1. "There is no relationship between heart disease and saturated fat." This is an example of:

a. hypothesis

b. mean

c. cluster sampling research

d. null hypothesis

2. Over the period of 15 years, a study examines sugar consumption. What type of study is this?

a. Longitudinal

b. Correlational

c. Prospective

d. Quantitative

3. Which of the following looks at a variable that is believed to lead to specific outcome?

a. longitudinal

b. prospective

c. correlational

d. quantitative

4. You are conducting a study to evaluate the effects of saturated fat on body fat percentage. What is the dependent variable?

a. saturated fat

b. both are dependent

c. none of these

d. body fat

5. You are conducting a study to evaluate the effects of saturated fat on body fat percentage. What is the independent variable?

a. body fat

b. both are independent

c. Saturated fat

d. none of these

6. You are conducting a study to evaluate the effects of saturated fat on body fat percentage. The null hypothesis would be:

a. there is no significant relationship between saturated fat intake and body fat percentage

b. saturated fat intake is positively correlated with body fat percentage

c. there is no null hypothesis for this study

d. there is a significant relationship between saturated fat intake and body fat percentage

7. When gathering a sample for your study, you selected subjects in the general population and categorized them as smokers and non smokers. Which type of sample do you have?

a. random sample

b. stratified random sample

c. cluster sample

d. none of these

8. From a study, the values collected for a variable are: 12, 8, 7, 4, 7, 2, 6, 1. What is the mean?

a. 8

b. 10

c. 6

d. 4

9. From a study, the values collected for a variable are: 12, 8, 7, 4, 7, 2, 6, 1. What is the mode?

a. 7

b. 4

c. 8

d. 6

10. From a study, the values collected for a variable are: 12, 8, 7, 4, 7, 2, 6, 1. What is the median?

a. 6

b. 4

c. 7

d. 8

11. For a normal distribution of standard deviation, what is the shape of the curve?

a. U shaped

b. S shaped

c. none of these

d. bell shaped

12. You have 31 subjects in your study. How many degrees of freedom do you have?

a. 31

b. 29

c. 30

d. 32

13. A .01 significance level indicates:

a. 10 out of 100 times the correlation of variables occurred by chance

b. 1 out of 100 times the correlation of variables occurred by chance

c. 1 out of 1000 times the correlation of variables occurred by chance

d. .01 out of 100 times the correlation of variables occurred by chance

14. Which of the following is used to prove relationship between 2 categorical variables?

a. chi-square test

b. Mean

c. Standard deviation

d. T-test

15. Which of the following shows whether differences between means of groups are significant?

a. T-test

b. Mean

c. Standard deviation

d. Chi-square test

16. The median of a distribution of scores is the:

a. the sum average of all scores

b. score occurring most frequently

c. none of these

d. score at the midpoint of the distribution

17. Which of the following P-value is most significant?

a. .001

b. .1

c. .0001

d. .5

18. A study with 7 subjects reveals BMIs of 40, 24, 37, 32, 52, 24, and 27. The mean BMI from this study is _____ and is correlated with ______.

a. 32; increased risk for morbidity or mortality

b. 33.7; increased risk for morbidity or mortality

c. 32; normal levels

d. 24; increased risk for morbidity or mortality

19. The effect of caffeine intake on heart rate was studied. Over 2-week period of time ½ the subjects were given caffeinated beverages and the control group was given beverages containing no caffeine. What is the dependent variable?

a. caffeine

b. heart rate

c. none of these

d. beverages

20. The effect of caffeine intake on heart rate was studied. Over 2-week period of time ½ the subjects were given caffeinated beverages and the control group was given beverages containing no caffeine What is the independent variable?

a. beverages

b. heart rate

c. none of these

d. caffeine

21. If the subjects and the researchers are unaware of who is receiving caffeinated beverages, what type of study is being used?

a. single blind

b. basic blind

c. double blind

d. triple blind

22. When evaluating correlational relationships, which of the following coefficients describe the most significant correlation?

a. .9

b. .5

c. -.5

d. .2

23. Test results include: 88, 92, 64, 77, 52. What is the median of the test results?

a. 64

b. 52

c. 88

d. 77

24. By randomizing samples, the researcher is attempting to avoid:

a. null hypothesis

b. bias

c. low significance

d. reliability

25. Nutrition analysis of 5 patients' diet recall reveals they have consumed the following amount of calories: 1408, 1947, 3023, 2221, and 3535. What is the median and mean, respectively, of the calories consumed?

a. 2427; 2221

b. 1213; 2221

c. 1213; 2427

d. 2221; 2427

Module 20 – Domain III Quiz
Research
1. "There is no relationship between heart disease and saturated fat." This is an example of: Correct
a. hypothesis
b. mean
c. cluster sampling research
d. null hypothesis
The null hypothesis states that no relationship exists among the variables being tested; research - tries to reject the null hypothesis.
2. Over the period of 15 years, a study examines sugar consumption. What type of study is this? Correct
a. Longitudinal
b. Correlational
c. Prospective
d. Quantitative
Longitudinal study designs look at variables over time.
3. Which of the following looks at a variable that is believed to lead to specific outcome? Correct
a. longitudinal
b. prospective
c. correlational
d. quantitative
Prospective study designs look at a variable that is believed to lead to a specific outcome.
4. You are conducting a study to evaluate the effects of saturated fat on body fat percentage. What is the dependent variable? Correct
a. saturated fat
b. both are dependent
c. none of these
d. body fat
Body fat is the dependent variable; variable outcome.
5. You are conducting a study to evaluate the effects of saturated fat on body fat percentage. What is the independent variable? Correct
a. body fat
b. both are independent
c. Saturated fat
d. none of these
Saturated fat is the independent variable; variables which are believed to influence the dependent variable.
6. You are conducting a study to evaluate the effects of saturated fat on body fat percentage. The null hypothesis would be: Correct
a. there is no significant relationship between saturated fat intake and body fat percentage
b. saturated fat intake is positively correlated with body fat percentage
c. there is no null hypothesis for this study
d. there is a significant relationship between saturated fat intake and body fat percentage
A null hypothesis states no relationship exists among the variables being tested; in research try to reject the null hypothesis.
7. When gathering a sample for your study, you selected subjects in the general population and categorized them as smokers and non smokers. Which type of sample do you have? Incorrect
a. random sample
b. stratified random sample
c. cluster sample
d. none of these
A stratified random sample is a large group broken down into subgroups based on certain characteristics; subjects are then randomly selected from subgroups.
8. From a study, the values collected for a variable are: 12, 8, 7, 4, 7, 2, 6, 1. What is the mean? Correct
a. 8
b. 10
c. 6
d. 4
The mean is the average; scores are added and divided by the number of scores.
9. From a study, the values collected for a variable are: 12, 8, 7, 4, 7, 2, 6, 1. What is the mode? Correct
a. 7
b. 6
c. 4
d. 8
The mode is the score that occurs most often.
10. From a study, the values collected for a variable are: 12, 8, 7, 4, 7, 2, 6, 1. What is the median? Correct
a. 6
b. 4
c. 7
d. 8
Median is the score at the midpoint of the distribution. Ordering the numbers in descending value 12,8,7,7,6,4,2,1; the median is between 7 and 6 (4th and 5th number in descending value). 7+6=13 divided by 2 = 6.5 or rounding up, 7.
11. For a normal distribution of standard deviation, what is the shape of the curve? Correct
a. U shaped
b. S shaped
c. none of these
d. bell shaped
The standard deviation is the amount a value deviates from the mean or the average; normal distribution = bell shaped curve.
12. You have 31 subjects in your study. How many degrees of freedom do you have? Correct
a. 31
b. 29
c. 30
d. 32
Degrees of freedom = number in the sample - 1 (n = number in sample; n - 1).
13. A .01 significance level indicates: Correct
a. 10 out of 100 times the correlation of variables occurred by chance
b. 1 out of 100 times the correlation of variables occurred by chance
c. .01 out of 100 times the correlation of variables occurred by chance
d. 1 out of 1000 times the correlation of variables occurred by chance
A .01 significance level indicates 1 out of 100 times the correlation of variables occurred by chance.
14. Which of the following is used to prove relationship between 2 categorical variables? Correct
a. chi-square test
b. T-test
c. Mean
d. Standard deviation
Chi-square test is used to prove relationship between two classified or categorical variables.
15. Which of the following shows whether differences between means of groups are significant? Correct
a. T-test
b. Mean
c. Standard deviation
d. Chi-square test
A T-test shows whether differences between means of groups are significant.
16. The median of a distribution of scores is the: Correct
a. the sum average of all scores
b. score occurring most frequently
c. none of these
d. score at the midpoint of the distribution
The median is the score at the midpoint of the distribution.
17. Which of the following P-value is most significant? Correct
a. .001
b. .1
c. .0001
d. .5
The smallest number for a P-value is the most significant; therefore .0001 is most significant.
18. A study with 7 subjects reveals BMIs of 40, 24, 37, 32, 52, 24, and 27. The mean BMI from this study is _____ and is correlated with ______. Correct
a. 32; increased risk for morbidity or mortality
b. 33.7; increased risk for morbidity or mortality
c. 32; normal levels
d. 24; increased risk for morbidity or mortality
Mean is an average, scores added together and divided by the number of scores. Recall from Module 5, a BMI above 25 is associated with risk for morbidity or mortality.
19. The effect of caffeine intake on heart rate was studied. Over 2-week period of time ½ the subjects were given caffeinated beverages and the control group was given beverages containing no caffeine What is the dependent variable? Correct
a. caffeine
b. heart rate
c. none of these
d. beverages
The dependent variable is the variable outcome.
20. The effect of caffeine intake on heart rate was studied. Over 2-week period of time ½ the subjects were given caffeinated beverages and the control group was given beverages containing no caffeine What is the independent variable? Correct
a. beverages
b. heart rate
c. none of these
d. caffeine
Independent variables are variables which are believed to influence the dependent variable.
21. If the subjects and the researchers are unaware of who is receiving caffeinated beverages, what type of study is being used? Correct
a. single blind
b. basic blind
c. double blind
d. triple blind
A double blind study is one where subjects and researchers are unaware of who is in the placebo and who is in the test group.
22. When evaluating correlational relationships, which of the following coefficients describe the most significant correlation? Correct
a. .9
b. .5
c. -.5
d. .2
A correlation should be close to 1 or -1 to indicate significance; a correlation close to zero indicates little or no significance.
23. Test results include: 88, 92, 64, 77, 52. What is the median of the test results? Correct
a. 64
b. 52
c. 88
d. 77
The median is the score at the middle of the distribution.
24. By randomizing samples, the researcher is attempting to avoid: Correct
a. null hypothesis
b. bias
c. reliability
d. low significance
Bias is a conscious or unconscious distortion of results by the researcher.
25. Nutrition analysis of 5 patients' diet recall reveals they have consumed the following amount of calories: 1408, 1947, 3023, 2221, and 3535. What is the median and mean, respectively, of the calories consumed? Correct
a. 2427; 2221
b. 1213; 2221
c. 1213; 2427
d. 2221; 2427
Median is the score at the middle of the distribution; Mean is the average, scores added together and divided by the number of scores.